Selection of Viola–Jones algorithm parameters for specific conditions

Egorov, Aleksej D.; Shtanko, A. N.; Mitrouchev, Peter

doi:10.3103/s1068335615080060

Cited by 18 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the features training process for the generation of eligible candidates from the large pool of classifiers for the task of detection, it is always desirable to achieve the required performance of classification task with the reduced set of features. A significant amount of research [1,3,4,5] has been donein the field of statistical analysis of features and modifications of the selection criteria of features inAdaBoost algorithm for achieving better performance of object detection.…”

Section: *Author For Correspondencementioning

confidence: 99%

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Mutneja¹,

Singh²

2021

IJATEE

View full text Add to dashboard Cite

Haar features have been used in most of the works in literature as key components in the task of object as well as face detection. Training of Haar features is an important step in the development of overall machine learning based face detection system. In this work, we have done investigation in the variations of a number of training parameters during AdaBoost based machine learning of Haar features with respect to size of training images. A number of observations have been drawn based on the variations of these parameters during training process. Training parameters True Detection Rate and Figure of Merit have been used as weighing parameter in formation of detection cascade for improvement in original AdaBoost framework used for machine learning of Haar features. Statistical analysis based on variations of training parameters has been done for selection of efficient learners from a large pool of available features which further are cascaded to make the strong classifiers.we have been able to achieve the maximum percentage reduction in training time of 47.20 corresponding to training images size 25x25 pixels with the help of statistical screening of Haar features prior to AdaBoost. The proposed system has been developed using training dataset from CBCL and successfully tested on facial images from datasets WIDER FACE a Face Detection Benchmark dataset, Annotated Faces in the Wild (AFW) and Face Detection Data Set and Benchmark (FDDB). and been able to achieve promising results in terms of training time computedin range of 0.31-2.83hrs, maximum detection rate 96.21% and minimum detection time16.95ms.

show abstract

Section: *Author For Correspondencementioning

confidence: 99%

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Mutneja¹,

Singh²

2021

IJATEE

View full text Add to dashboard Cite

show abstract

“…The learning algorithm is based on AdaBoost which selects a small number of important features from a large set and gives highly competent classifiers and is used to create strong classifier from combining a collection of weak classification functions. The complex classifiers are combined to form a 'cascade' which discard any non-face regions in an image [4]. The image (matrix) I is transformed to an integral image representing a certain matrix L whose sizes coincide with sizes of the initial image as given in the Equation (1).…”

Section: Preprocessingmentioning

confidence: 99%

Analysis of Micro Facial Expression by Machine and Deep Learning Methods: Haar, CNN, and RNN

Pant

Sthapit

2021

J. Inst. Engineering

View full text Add to dashboard Cite

Facial expressions are due to the actions of the facial muscles located at different facial regions. These expressions are two types: Macro and Micro expressions. The second one is more important in computer vision. Analysis of micro expressions categorized by disgust, happiness, anger, sadness, surprise, contempt, and fear are challenging because of very fast and subtle facial movements. This article presents one machine learning method: Haar and two deep learning methods: Convolution Neural Network (CNN) and Recurrent Neural Network (RNN) to perform recognition of micro-facial expression analysis. First, Haar Cascade Classifier is used to detect the face as a pre-image-processing step. Secondly, those detected faces are passed through series of Convolutional Neural Network (CNN) layers for the features extraction. Thirdly, the Recurrent Neural Network (RNN) classifies micro facial expressions. Two types of data sets are used for training and testing of the proposed method: Chinese Academy of Sciences Micro-Expression II (CSAME II) and Spontaneous Actions and Micro-Movements (SAMM) database. The test accuracy of SAMM and CASME II are obtained as 84.76%, and 87% respectively. In addition, the distinction between micro facial expressions and non- micro facial expressions are analyzed by the ROC curve.

show abstract

“…Sidik jari dan wajah manusia merupakan objek biometrik yang mudah dipindai dan diproses. Banyak algoritma yang telah dikembangkan oleh peneliti sebelumnya yang berhasil melakukan identifikasi (Azzeh, 2012;Egorov, Shtanko, & Minin, 2015;Kurniawan et al, 2014).…”

Section: Pendahuluanunclassified

Eksperimen Pengenalan Wajah dengan fitur Indoor Positioning System menggunakan Algoritma CNN

Hartiwi

Rasywir

Pratama

et al. 2020

Jurnal Sistem Informasi, Teknik Informatika, Software Engineeri

View full text Add to dashboard Cite

Facial recognition work combined with the facial owner's position estimation feature can be utilized in various everyday applications such as face attendance with position detection. Based on this, this study offers a system testing experiment that can be run with facial recognition features and an Indoor Positioning System (IPS) to automatically check the location of the owner of the face. Recently, deep learning algorithms are the most popular method in the world of artificial intelligence. Currently, the Deep Learning algorithm toolbox has provided various programming language platforms. Departing from research findings related to deep learning, this study utilizes this method to perform facial recognition. The system we offer is also capable of checking the position or whereabouts of objects using Indoor Positioning System (IPS) technology. Facial recognition evaluation using CNN obtained a maximum value = 92.89% and an accuracy error value of 7.11%. Meanwhile, the average accuracy obtained is 91.86%. In the evaluation of the estimated position tested using DNN, the highest value of r2 score is 0.934, the lowest is 0.930 and an average is 0.932 and the highest value is MSE is 4.578, the lowest is 4.366 and the average is 4.475. This shows that the facial recognition process that is tested is able to produce good values but not the position estimation process. Keywords: Face Recognition, IPS, CNN, MSE, Accuraccy.

show abstract

Selection of Viola–Jones algorithm parameters for specific conditions

Cited by 18 publications

References 2 publications

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Haar-features training parameters analysis in boosting based machine learning for improved face detection

Analysis of Micro Facial Expression by Machine and Deep Learning Methods: Haar, CNN, and RNN

Eksperimen Pengenalan Wajah dengan fitur Indoor Positioning System menggunakan Algoritma CNN

Contact Info

Product

Resources

About